{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NUGHDQOTKGZX4A5ARCFCXU4EE7","short_pith_number":"pith:NUGHDQOT","canonical_record":{"source":{"id":"2507.08793","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T17:54:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc89cde79e4fb3a6e0bf515a841f6e09537dc0bf95cc93b2f0c8ca1d53a75652","abstract_canon_sha256":"536886091cdf77179494322c7185369317d3af04750fda599a7681418151967f"},"schema_version":"1.0"},"canonical_sha256":"6d0c71c1d351b37e03a0888a2bd38427f3e70e7aedffa5eea1d5553526d4f188","source":{"kind":"arxiv","id":"2507.08793","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08793","created_at":"2026-07-05T12:00:04Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08793v2","created_at":"2026-07-05T12:00:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08793","created_at":"2026-07-05T12:00:04Z"},{"alias_kind":"pith_short_12","alias_value":"NUGHDQOTKGZX","created_at":"2026-07-05T12:00:04Z"},{"alias_kind":"pith_short_16","alias_value":"NUGHDQOTKGZX4A5A","created_at":"2026-07-05T12:00:04Z"},{"alias_kind":"pith_short_8","alias_value":"NUGHDQOT","created_at":"2026-07-05T12:00:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NUGHDQOTKGZX4A5ARCFCXU4EE7","target":"record","payload":{"canonical_record":{"source":{"id":"2507.08793","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T17:54:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc89cde79e4fb3a6e0bf515a841f6e09537dc0bf95cc93b2f0c8ca1d53a75652","abstract_canon_sha256":"536886091cdf77179494322c7185369317d3af04750fda599a7681418151967f"},"schema_version":"1.0"},"canonical_sha256":"6d0c71c1d351b37e03a0888a2bd38427f3e70e7aedffa5eea1d5553526d4f188","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:04.073535Z","signature_b64":"TD0iHocbVxyI0EMKbUQ/LeiX5rARNczjCnw14HT83ebEvpNaOOApYwLF2uekHu3fbgR3+CK1nTtAGwachPfeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d0c71c1d351b37e03a0888a2bd38427f3e70e7aedffa5eea1d5553526d4f188","last_reissued_at":"2026-07-05T12:00:04.073108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:04.073108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.08793","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:00:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AZj8orya4awD5rOBEeqUtZ7ULAPOmJycvmHXEL99PGGm7BwRpSsr4VBhtYRDX7pOnNCibPBNXQFRuXMgFp2sDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:03:07.163040Z"},"content_sha256":"db69cf9b5f33db117cc9764cc2106c4cd23a19e75546d6d2223ba09748e79df9","schema_version":"1.0","event_id":"sha256:db69cf9b5f33db117cc9764cc2106c4cd23a19e75546d6d2223ba09748e79df9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NUGHDQOTKGZX4A5ARCFCXU4EE7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimistic Exploration for Risk-Averse Constrained Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Elizabeth Daly, Ivana Dusparic, James McCarthy, Radu Marinescu","submitted_at":"2025-07-11T17:54:54Z","abstract_excerpt":"Risk-averse Constrained Reinforcement Learning (RaCRL) aims to learn policies that minimise the likelihood of rare and catastrophic constraint violations caused by an environment's inherent randomness. In general, risk-aversion leads to conservative exploration of the environment which typically results in converging to sub-optimal policies that fail to adequately maximise reward or, in some cases, fail to achieve the goal. In this paper, we propose an exploration-based approach for RaCRL called Optimistic Risk-averse Actor Critic (ORAC), which constructs an exploratory policy by maximising a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08793","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.08793/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:00:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bZdJvL+d8j2WLNF2HXf41RIycIiaTnOaL8e7daCg9gYoERPh4fE1FEBUljepyF2vd8gCyv7Z9BkCNBfUas30DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:03:07.163597Z"},"content_sha256":"9a6a133085cf2c0b04b14f8e5615e6f8b44116db5185ae8382052aa7bbea51d6","schema_version":"1.0","event_id":"sha256:9a6a133085cf2c0b04b14f8e5615e6f8b44116db5185ae8382052aa7bbea51d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NUGHDQOTKGZX4A5ARCFCXU4EE7/bundle.json","state_url":"https://pith.science/pith/NUGHDQOTKGZX4A5ARCFCXU4EE7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NUGHDQOTKGZX4A5ARCFCXU4EE7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T07:03:07Z","links":{"resolver":"https://pith.science/pith/NUGHDQOTKGZX4A5ARCFCXU4EE7","bundle":"https://pith.science/pith/NUGHDQOTKGZX4A5ARCFCXU4EE7/bundle.json","state":"https://pith.science/pith/NUGHDQOTKGZX4A5ARCFCXU4EE7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NUGHDQOTKGZX4A5ARCFCXU4EE7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NUGHDQOTKGZX4A5ARCFCXU4EE7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"536886091cdf77179494322c7185369317d3af04750fda599a7681418151967f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T17:54:54Z","title_canon_sha256":"dc89cde79e4fb3a6e0bf515a841f6e09537dc0bf95cc93b2f0c8ca1d53a75652"},"schema_version":"1.0","source":{"id":"2507.08793","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08793","created_at":"2026-07-05T12:00:04Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08793v2","created_at":"2026-07-05T12:00:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08793","created_at":"2026-07-05T12:00:04Z"},{"alias_kind":"pith_short_12","alias_value":"NUGHDQOTKGZX","created_at":"2026-07-05T12:00:04Z"},{"alias_kind":"pith_short_16","alias_value":"NUGHDQOTKGZX4A5A","created_at":"2026-07-05T12:00:04Z"},{"alias_kind":"pith_short_8","alias_value":"NUGHDQOT","created_at":"2026-07-05T12:00:04Z"}],"graph_snapshots":[{"event_id":"sha256:9a6a133085cf2c0b04b14f8e5615e6f8b44116db5185ae8382052aa7bbea51d6","target":"graph","created_at":"2026-07-05T12:00:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.08793/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Risk-averse Constrained Reinforcement Learning (RaCRL) aims to learn policies that minimise the likelihood of rare and catastrophic constraint violations caused by an environment's inherent randomness. In general, risk-aversion leads to conservative exploration of the environment which typically results in converging to sub-optimal policies that fail to adequately maximise reward or, in some cases, fail to achieve the goal. In this paper, we propose an exploration-based approach for RaCRL called Optimistic Risk-averse Actor Critic (ORAC), which constructs an exploratory policy by maximising a ","authors_text":"Elizabeth Daly, Ivana Dusparic, James McCarthy, Radu Marinescu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T17:54:54Z","title":"Optimistic Exploration for Risk-Averse Constrained Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08793","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:db69cf9b5f33db117cc9764cc2106c4cd23a19e75546d6d2223ba09748e79df9","target":"record","created_at":"2026-07-05T12:00:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"536886091cdf77179494322c7185369317d3af04750fda599a7681418151967f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T17:54:54Z","title_canon_sha256":"dc89cde79e4fb3a6e0bf515a841f6e09537dc0bf95cc93b2f0c8ca1d53a75652"},"schema_version":"1.0","source":{"id":"2507.08793","kind":"arxiv","version":2}},"canonical_sha256":"6d0c71c1d351b37e03a0888a2bd38427f3e70e7aedffa5eea1d5553526d4f188","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d0c71c1d351b37e03a0888a2bd38427f3e70e7aedffa5eea1d5553526d4f188","first_computed_at":"2026-07-05T12:00:04.073108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:04.073108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TD0iHocbVxyI0EMKbUQ/LeiX5rARNczjCnw14HT83ebEvpNaOOApYwLF2uekHu3fbgR3+CK1nTtAGwachPfeAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:04.073535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.08793","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db69cf9b5f33db117cc9764cc2106c4cd23a19e75546d6d2223ba09748e79df9","sha256:9a6a133085cf2c0b04b14f8e5615e6f8b44116db5185ae8382052aa7bbea51d6"],"state_sha256":"9577d77469214bdd520817260153bd888b0ec4c5e335d148dd6eca95decec71f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jwg1hKQRyXNU7XodWRvvlO3NZgM8cpEwL2xnae5Xj8F3e7BpwLKHRbbPtpbG1LYdF7Pv8DQGJ2EaOx+xROGmBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:03:07.167144Z","bundle_sha256":"4a4763c6894e2b2c4363774af215b629733ea667fad587d23ba48e5be848ff9a"}}